Machine unlearning for governance of foundation models Sijia Liu, Yang Liu, Nathalie Baracaldo, editors

Format:

Book

Author/Creator:

Liu, Sijia

Contributor:

Liu, Sijia, editor.

Liu, Yang, editor.

Baracaldo, Nathalie, editor.

Series:

Synthesis lectures on computer vision 2153-1064

Language:

English

Subjects (All):

Machine learning.

Physical Description:

1 online resource

Place of Publication:

Cham Springer [2026]

System Details:

text file PDF

Summary:

This book provides a systematic and in-depth introduction to machine unlearning (MU) for foundation models, framed through an optimization-model-data tri-design perspective and complemented by assessments and applications. As foundation models are continuously adapted and reused, the ability to selectively remove unwanted data, knowledge, or model behavior, without full retraining, poses new theoretical and practical challenges. Thus, MU has become a critical capability for trustworthy, deployable, and regulation-ready artificial intelligence. From the optimization viewpoint, this book treats unlearning as a multi-objective and often adversarial problem that must simultaneously enforce targeted forgetting, preserve model utility, resist recovery attacks, and remain computationally efficient. From the model perspective, the book examines how knowledge is distributed across layers and latent subspaces, motivating modular and localized unlearning. From the data perspective, the book explores forget-set construction, data attribution, corruption, and coresets as key drivers of reliable forgetting. Bridging theory and practice, the book also provides a comprehensive review of benchmark datasets and evaluation metrics for machine unlearning, critically examining their strengths and limitations. The authors further survey a wide range of applications in computer vision and large language models, including AI safety, privacy, fairness, and industrial deployment, highlighting why post-training model modification is often preferred over repeated retraining in real-world systems. By unifying optimization, model, data, evaluation, and application perspectives, this book offers both a foundational framework and a practical toolkit for designing machine unlearning methods that are effective, robust, and ready for large-scale, regulated deployment. In addition, this book: Introduces the technical foundations of MU and its distinctions from fine-tuning, editing, and alignment methods Offers guiding principles across optimization, model, data, and evaluation for designing effective unlearning solutions Covers emerging vision and language applications of MU, with a focus on trustworthy and safe generative AI

Contents:

Introduction

Concept Dissection of MU

Algorithmic Foundations of MU

Evaluation Metrics and Methods of MU

Applications

Conclusion and Prospects

Notes:

Online resource; title from PDF title page (SpringerLink, viewed June 16, 2026)

ISBN:

9783032172822

3032172829

OCLC:

1596214141